Segmentation-based emerging content-based image retrieval systems enable the user to perform object-based database querying. We propose an integrated segmentation technique for interactive image retrieval, that is reasonably accurate and fast. An initial oversegmentation is generated by finding the dominant color modes in the global histogram of the image using the mean-shift algorithm. Edge-based processing is performed at the initial segment boundaries to merge non-obvious segments. Finally segment shapes are regularized using the Hopfield network and competitive learning to improve their perceptual quality. Scalable implementations are presented for ensuring fast serial execution of neural networks. The entire segmentation process takes less than ten seconds to segment 128x192 stock photos on a standard workstation.
By: R. Aditya, Sugata Ghosal
Published in: IEEE International Conference on Image Processing (ICIP 2000), Vancouver, BC, Canada, September 2000., IEEE in 2000
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .